© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116401
    Prev
    Next
    INDEX
    Explanations

    oligohydramnion, voluminous echogenic, hyperlaxity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inhum
    -0.07
    Name
    -0.06
    判
    -0.06
    paragraphs
    -0.06
     abusive
    -0.06
    πά
    -0.06
    🕴
    -0.06
     समुदाय
    -0.06
     tragedia
    -0.06
     জগতের
    -0.06
    POSITIVE LOGITS
     naturally
    0.07
     all
    0.07
     Naturally
    0.07
     sedikit
    0.07
     one
    0.07
     remarqué
    0.06
    Naturally
    0.06
     natürlich
    0.06
     These
    0.06
     ONE
    0.06
    Activations Density 0.022%

    No Known Activations